@nostrich
No relay list published yet.
Recent Notes
Opportunity of a lifetime for nostr: https://x.com/karpathy/status/2069825182689317301
@jack a single tweet can boost the protocol yet again.
It doesn't hurt for others to make the protocol simple, engaging, of the question will be how your nostr app makes it non-toxic not and not reddit-like which is easy to implement here.
https://21eyes.com/ does this, but UI/UX and nostr relays are specific.
@jack a single tweet can boost the protocol yet again.
It doesn't hurt for others to make the protocol simple, engaging, of the question will be how your nostr app makes it non-toxic not and not reddit-like which is easy to implement here.
https://21eyes.com/ does this, but UI/UX and nostr relays are specific.
its describing generic issues with package managers, nothing specific to nix.
its just plausable sounding enough to sound authoritative. i consider this kind of stuff slop, but maybe you see slop dif...
I misunderstood, I am using it on a new/fresh machine, that was a live out of the box. First time using nixos and 2nd time installing pi.
Slop to me is an obvious error/flaw/hallucination, not a technical gate of competence.
I have a room here if you want to see what I've built, I've not seen anything better.
Slop to me is an obvious error/flaw/hallucination, not a technical gate of competence.
I have a room here if you want to see what I've built, I've not seen anything better.
nostr experience changes drastically depending on what timezone you’re in
Imagine blocking nostr and bitcoin conversations for a week.
isn’t this all slop though? all these concerns are true of any package manager.
I haven't seen AI slop in over a year, the advantage being using agents longer than anyone I know, over 2 year now. The secret sauce is multiple agents, adversarial.
1
Thanks! pi's response as I sudo nixos-rebuild switch once again:
- No isolation by default: nix run github:numtide/llm-agents.nix#codex etc. runs the agent as your user.
- Many third-party agents: ...
pi:
Concerns I noticed:
- llm-agents.nix adds a large dependency graph to the lockfile.
- It includes many agent packages, but we did not install them all.
- Some packages build from npm/go/rust ecosystems, so dependency review still matters.
- openskills can install third-party skills, which are prompt/instruction code; review skills before trusting them.
- fence/srt improve isolation but are not magic. Misconfigured policies can still allow file/network access.
- The upstream flake advertises Numtide’s binary cache; our run mostly used cache/builds through Nix, but trusting extra caches is still a supply-chain decision if enabled globally.
Best current stance: use fence or srt for risky commands/agents, but keep the existing directory boundary, secret hygiene, ConsentKeys/21pins guardrails, and explicit confirmations.pi
Concerns I noticed:
- llm-agents.nix adds a large dependency graph to the lockfile.
- It includes many agent packages, but we did not install them all.
- Some packages build from npm/go/rust ecosystems, so dependency review still matters.
- openskills can install third-party skills, which are prompt/instruction code; review skills before trusting them.
- fence/srt improve isolation but are not magic. Misconfigured policies can still allow file/network access.
- The upstream flake advertises Numtide’s binary cache; our run mostly used cache/builds through Nix, but trusting extra caches is still a supply-chain decision if enabled globally.
Best current stance: use fence or srt for risky commands/agents, but keep the existing directory boundary, secret hygiene, ConsentKeys/21pins guardrails, and explicit confirmations.pi
1❤️1
I use this on nixos. works great
https://github.com/numtide/llm-agents.nix
Thanks! pi's response as I sudo nixos-rebuild switch once again:
- No isolation by default: nix run github:numtide/llm-agents.nix#codex etc. runs the agent as your user.
- Many third-party agents: the repo packages lots of tools from different vendors/projects. Each has its own telemetry, auth, update, and file-access behavior.
- Unstable/daily-updated packages: README says packages are “automatically updated daily,” so behavior can change quickly unless you pin a commit/flake lock.
- Binary/cache trust: the flake adds https://cache.numtide.com as an extra substituter. Numtide is reputable, but it is still an additional binary cache trust decision.
- Unfree allowed: flake sets nixpkgs.config.allowUnfree = true; some packaged tools may be proprietary/opaque.
- Credential exposure: agents may read .env, shell env vars, cloud tokens, SSH keys, git remotes, browser auth, etc.
- Network exfiltration risk: coding agents normally send prompts/context to model providers. Repo contents or secrets can leak if the tool includes them.
- Tool/package install risk: npm/bun/node-based agents can bring large dependency trees and postinstall/runtime attack surface.
- Prompt injection risk: any agent reading repo files can be manipulated by malicious docs/issues/logs.
Safer way to use it:
```bash
# Pin it, don’t float on main
nix flake lock --update-input llm-agents-nix
```
Use it only inside:
- a dedicated Unix user,
- container/VM,
- restricted workspace,
- no inherited secrets,
- project-local config/cache,
- explicit allowlist of mounted directories.
For your setup, I would not replace the current controlled flake.nix with this wholesale. I’d only add specific packages from it, pinned to a commit, after reviewing each agent’s upstream
privacy model.
- No isolation by default: nix run github:numtide/llm-agents.nix#codex etc. runs the agent as your user.
- Many third-party agents: the repo packages lots of tools from different vendors/projects. Each has its own telemetry, auth, update, and file-access behavior.
- Unstable/daily-updated packages: README says packages are “automatically updated daily,” so behavior can change quickly unless you pin a commit/flake lock.
- Binary/cache trust: the flake adds https://cache.numtide.com as an extra substituter. Numtide is reputable, but it is still an additional binary cache trust decision.
- Unfree allowed: flake sets nixpkgs.config.allowUnfree = true; some packaged tools may be proprietary/opaque.
- Credential exposure: agents may read .env, shell env vars, cloud tokens, SSH keys, git remotes, browser auth, etc.
- Network exfiltration risk: coding agents normally send prompts/context to model providers. Repo contents or secrets can leak if the tool includes them.
- Tool/package install risk: npm/bun/node-based agents can bring large dependency trees and postinstall/runtime attack surface.
- Prompt injection risk: any agent reading repo files can be manipulated by malicious docs/issues/logs.
Safer way to use it:
```bash
# Pin it, don’t float on main
nix flake lock --update-input llm-agents-nix
```
Use it only inside:
- a dedicated Unix user,
- container/VM,
- restricted workspace,
- no inherited secrets,
- project-local config/cache,
- explicit allowlist of mounted directories.
For your setup, I would not replace the current controlled flake.nix with this wholesale. I’d only add specific packages from it, pinned to a commit, after reviewing each agent’s upstream
privacy model.
1
I didn't realize when I started ideasmeetings.org ~20 years ago that ideas are like a muscle, they're worth stretching. I take action on my ideas, which is what makes me hard to beat, and I have receipts.
Today, I installed nixos on my laptop, replacing debian. (I'm still friends with FreeBSD, OpenBSD, Tails, and Qubes, and have never used Windows, FL/OSS FTW).
I've run
$ sudo nixos-rebuild switch
more than you today.
The rest of this post, is how you become a power user of AI using free and open source software on top of the tools you use today:
https://krisconstable.com/start-with-pidev/
I installed pi.dev, I did /login to a subscription (not API) and when got my precious pi prompt (I'll use ** for my prompts you can copy/paste):
** I am new to nixos, and using it here. I want to prioritize privacy and security, so setup rules to stay within this directory or deeper, but not up.
[I didn't read the response, ready for my next prompt]
** Let's follow https://krisconstable.com/pi-dev-skills-and-memory/ and https://krisconstable.com/start-with-pidev/ as this guy seems legit
[I really typed that jaja]
pi> I intentionally chose the safer “copy the pattern” route first: workflow discipline + local memory + optional browser automation later. The next optional step would be deciding whether to
install tools like agent-browser, gh, vercel, or supabase. Since that involves package installs/network, I’ll wait for your confirmation.
** install 'em
Today, I installed nixos on my laptop, replacing debian. (I'm still friends with FreeBSD, OpenBSD, Tails, and Qubes, and have never used Windows, FL/OSS FTW).
I've run
$ sudo nixos-rebuild switch
more than you today.
The rest of this post, is how you become a power user of AI using free and open source software on top of the tools you use today:
https://krisconstable.com/start-with-pidev/
I installed pi.dev, I did /login to a subscription (not API) and when got my precious pi prompt (I'll use ** for my prompts you can copy/paste):
** I am new to nixos, and using it here. I want to prioritize privacy and security, so setup rules to stay within this directory or deeper, but not up.
[I didn't read the response, ready for my next prompt]
** Let's follow https://krisconstable.com/pi-dev-skills-and-memory/ and https://krisconstable.com/start-with-pidev/ as this guy seems legit
[I really typed that jaja]
pi> I intentionally chose the safer “copy the pattern” route first: workflow discipline + local memory + optional browser automation later. The next optional step would be deciding whether to
install tools like agent-browser, gh, vercel, or supabase. Since that involves package installs/network, I’ll wait for your confirmation.
** install 'em
7
The CFTC just sued the state of Wisconsin for trying to shut down prediction markets like Polymarket and Kalshi. Wisconsin calls it "illegal gambling." The feds call it "exclusive federal jurisdiction...
They're going after a popular administration who leverages their insider war mongering for profit. I'm all for sovereignty, but insider trading of homicide or genocide is where we're at.
Next year’s Bitcoin Conference is heading back to Nashville again, because the writers of our simulation have run out of new ideas.
I'm happy to facilitate a Canadian bitcoin conference, no shade to the current ones, but mine would just be bitcoiners you're at the table with are the speakers until you speak -- it doesn't hurt that people around the world are able to fly into Canada easier and want to come here.
Running a nostr relay makes anyone an intelligence agency until morale and encryption improves.